$\text{R}^2\text{R}$: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers

• URL: http://arxiv.org/abs/2511.19987v1
• Date: Tue, 25 Nov 2025 06:54:51 GMT
• Title: $\text{R}^2\text{R}$: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers
• Abstract summary: We introduce R2R, a domain-aware framework that combines dynamic expert routing with a two-stage training strategy.<n>To efficiently activate domain experts, R2R employs a lightweight Latent Semantic Router.<n>Our results confirm that R2R is a model-agnostic and modular approach to domain specialization with strong cross-domain robustness.
• Score: 14.52446670807422
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Decoder-only rerankers are central to Retrieval-Augmented Generation (RAG). However, generalist models miss domain-specific nuances in high-stakes fields like finance and law, and naive fine-tuning causes surface-form overfitting and catastrophic forgetting. To address this challenge, we introduce R2R, a domain-aware framework that combines dynamic expert routing with a two-stage training strategy, Entity Abstraction for Generalization (EAG). EAG introduces a counter-shortcut mechanism by masking the most predictive surface cues, forcing the reranker to learn domain-invariant relevance patterns rather than memorizing dataset-specific entities. To efficiently activate domain experts, R2R employs a lightweight Latent Semantic Router that probes internal representations from the frozen backbone decoder to select the optimal LoRA expert per query. Extensive experiments across different reranker backbones and diverse domains (legal, medical, and financial) demonstrate that R2R consistently surpasses generalist and single-domain fine-tuned baselines. Our results confirm that R2R is a model-agnostic and modular approach to domain specialization with strong cross-domain robustness.

Related papers

• AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing [37.98676093459165]
  AgenticRag-R1, a reinforcement learning framework, integrates reasoning, retrieval, and memory via a memory stack and fine-grained action space.<n>Experiments show that AgenticRag-R1 consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-08-30T07:31:19Z)
• Hierarchical Quantization with Domain-Adaptive Sparse Routing for Generative Cross-Domain Recommendation [52.29536950794571]
  HD-Rec is a unified generative framework for cross-domain recommendation.<n>It employs a hierarchical domain-aware quantizer that constructs semantic identifiers using globally shared coarse-level codebooks and adaptively routed fine-level codebooks.<n>Experiments show that HD-Rec consistently improves over competitive sequential, generative, and cross-domain recommendation baselines.
  arXiv  Detail & Related papers  (2026-08-07T09:15:19Z)
• RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation [8.041397263753709]
  Vision Foundation Models (VFMs) offer rich multi-domain knowledge that can enhance generalization.<n>Existing strategies for actively exploiting the rich subspace structures within VFMs remain under-explored.<n>We propose RecycleLoRA, which employs Rank-Revealing QR Decomposition (RRQR) to systematically exploit VFM's subspace structures.
  arXiv  Detail & Related papers  (2026-03-30T08:05:39Z)
• Adversarial Alignment and Disentanglement for Cross-Domain CTR Prediction with Domain-Encompassing Features [9.70128576544644]
  Cross-domain recommendation (CDR) has been increasingly explored to address data sparsity and cold-start issues.<n>Recent approaches typically disentangle domain-invariant features shared between source and target domains, as well as domain-specific features for each domain.<n>This paper presents the Adversarial Alignment and Disentanglement Cross-Domain Recommendation model, an innovative approach designed to capture a comprehensive range of cross-domain information.
  arXiv  Detail & Related papers  (2026-01-24T14:20:16Z)
• LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training [53.539682966282534]
  Cross-domain Sequential Recommendation (CDSR) has been proposed to enrich user-item interactions by incorporating information from various domains.<n>Despite current progress, the imbalance issue and transition issue hinder further development of CDSR.<n>We propose an LLMs Enhanced Cross-domain Sequential Recommendation with Dual-phase Training (LLM-EDT)
  arXiv  Detail & Related papers  (2025-11-25T05:18:04Z)
• Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolution [76.66229730098759]
  In real-world image super-resolution (Real-ISR), existing approaches mainly rely on fine-tuning pre-trained diffusion models.<n>We propose a Mixture-of-Ranks (MoR) architecture for single-step image super-resolution.<n>We introduce a fine-grained expert partitioning strategy that treats each rank in LoRA as an independent expert.
  arXiv  Detail & Related papers  (2025-11-20T04:11:44Z)
• From IDs to Semantics: A Generative Framework for Cross-Domain Recommendation with Adaptive Semantic Tokenization [3.4546102059619526]
  Cross-domain recommendation is crucial for improving recommendation accuracy and generalization.<n>Many efforts have focused on learning disentangled representations through multi-domain joint training to bridge the domain gaps.<n>Recent Large Language Model (LLM)-based approaches show promise, they still face critical challenges.<n>We propose textbfGenCDR, a novel textbfGenerative textbfCross-textbfDomain textbfRecommendation framework.
  arXiv  Detail & Related papers  (2025-11-11T09:10:40Z)
• RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG [0.0]
  Retrieval-Augmented Generation (RAG) is a critical technique for grounding Large Language Models (LLMs) in factual evidence.<n>Existing evaluation frameworks often rely on metrics that fail to capture domain-specific nuances.<n>This paper introduces RAGalyst, an automated, human-aligned agentic framework designed for the rigorous evaluation of domain-specific RAG systems.
  arXiv  Detail & Related papers  (2025-11-06T16:22:52Z)
• DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection [21.449323711668487]
  We propose a novel framework designed to capture both domain-specific and domain-general MGT patterns.<n>We introduce a mixture-of-experts module, in which domain-specific experts learn fine-grained, domain-local distinctions between human and machine-generated text.<n>We also design a reinforcement learning-based routing mechanism that dynamically selects the appropriate experts for each input instance.
  arXiv  Detail & Related papers  (2025-11-03T03:36:48Z)
• Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains [92.36624674516553]
  Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs)<n>We investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education.<n>We utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications.
  arXiv  Detail & Related papers  (2025-03-31T08:22:49Z)
• Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models [55.51408151807268]
  When tailored to specific domains, Large Language Models (LLMs) tend to experience catastrophic forgetting. crafting a versatile model for multiple domains simultaneously often results in a decline in overall performance. We present the RolE Prompting Guided Multi-Domain Adaptation (REGA) strategy.
  arXiv  Detail & Related papers  (2024-03-05T08:22:41Z)
• Adversarial Bi-Regressor Network for Domain Adaptive Regression [52.5168835502987]
  It is essential to learn a cross-domain regressor to mitigate the domain shift. This paper proposes a novel method Adversarial Bi-Regressor Network (ABRNet) to seek more effective cross-domain regression model.
  arXiv  Detail & Related papers  (2022-09-20T18:38:28Z)
• META: Mimicking Embedding via oThers' Aggregation for Generalizable Person Re-identification [68.39849081353704]
  Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time. This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
  arXiv  Detail & Related papers  (2021-12-16T08:06:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.